TokenRate

DeepSeek V4 Pro 0813 Pricing

Flagship

DeepSeek · 1M tokens context

DeepSeek V4 Pro 0813 from DeepSeek costs $1.12 per 1 million input tokens and $3.36 per 1 million output tokens as of September 2026 (live OpenRouter data). The model supports a 1,048,576-token context window (approximately 786,432 words) with a 384K-token maximum output. A typical 1,000-token request costs $0.0011 in input charges; a 10,000-token request costs $0.0112.

DeepSeek V4 Pro 0813 pricing and capability summary
Input price$1.12 / 1M tokens
Output price$3.36 / 1M tokens
Output / input ratio3.0×
Context window1,048,576 tokens (~786,432 words)
Maximum output384,000 tokens
Cost per 1K tokens (input)$0.0011
TierFlagship
Last verified

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Live pricing from OpenRouter

Input Price

$1.12

per 1 million tokens

Output Price

$3.36

per 1 million tokens

Context Window

1M tokens

max 384K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.00149$0.00134
10-page document (2,500 words)3,333$0.00374$0.00336
1,000 lines of code5,000$0.0056$0.00504
100K token document100,000$0.1121$0.1009

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Massive 1M-token context window
  • Frontier-class quality on complex tasks
  • Strong general-purpose performance

Limitations

  • Quality and availability can vary by hosting provider
  • Quality and availability can vary by hosting provider

Best Use Cases

Complex research and analysis
Advanced coding and architecture
Long-form content generation
High-stakes production workloads

Calculate DeepSeek V4 Pro 0813 Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact DeepSeek V4 Pro 0813 costs — and compare across all models.

Open Calculator →

DeepSeek V4 Pro 0813 — FAQ

Related Models

Related Guides